Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1012 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Language Modeling | Portuguese evaluation suite (test) | 27 | Mar 5, 2026 | ||
| Long-term Question Answering | LoCoMo | 27 | Mar 5, 2026 | ||
| Instance Segmentation | NC4K | 27 | Mar 5, 2026 | ||
| Instance Segmentation | COD10K v3 (test) | 27 | Mar 5, 2026 | ||
| Decoding Throughput | GSM8k | 27 | Jun 2, 2026 | ||
| Decoding Throughput | HumanEval | 27 | Jun 2, 2026 | ||
| Video-driven Audio Hallucination | AVHBench | 27 | Apr 16, 2026 | ||
| Face Forgery Detection | Cross Domain Evaluation Summary | 27 | Mar 4, 2026 | ||
| Text-to-Image Retrieval | DOCCI (val) | 27 | Mar 4, 2026 | ||
| Image-to-Text Retrieval | DOCCI (val) | 27 | Mar 4, 2026 | ||
| Safety Alignment | BeaverTails V | 27 | Jun 4, 2026 | ||
| Verilog Code Generation | RTLLM v2 | 27 | May 14, 2026 | ||
| Robotic Manipulation | Meta-World | 27 | May 28, 2026 | ||
| Regression | airfoil | 27 | May 6, 2026 | ||
| Geolocation Inference | Location-related Privacy Leakage Dataset | 27 | Mar 4, 2026 | ||
| Image Captioning | COCO-LN 500 (test) | 27 | Mar 4, 2026 | ||
| LLM Alignment | HelpSteer (test) | 27 | Mar 4, 2026 | ||
| Safety Evaluation | VLGuard | 27 | Apr 28, 2026 | ||
| Offline Reinforcement Learning | Hopper Medium JointNoise Shift | 27 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | Hopper Medium BodyMass Shift | 27 | Mar 4, 2026 | ||
| Offline Reinforcement Learning | Walker2D Medium BodyMass Shift | 27 | Mar 4, 2026 | ||
| Solving integral equations | Two-dimensional integral equation | 27 | Mar 4, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 27 | Mar 4, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 27 | Mar 4, 2026 | ||
| Commonsense Reasoning | HellaSwag 10-shot | 27 | Apr 28, 2026 |